{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7530120481927711,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.2303,
      "step": 100
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.21,
      "step": 200
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.5e-06,
      "loss": 0.2118,
      "step": 300
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.2131,
      "step": 400
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.5e-06,
      "loss": 0.2076,
      "step": 500
    },
    {
      "epoch": 0.45,
      "learning_rate": 3e-06,
      "loss": 0.2116,
      "step": 600
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.5e-06,
      "loss": 0.2154,
      "step": 700
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.2129,
      "step": 800
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.5e-06,
      "loss": 0.211,
      "step": 900
    },
    {
      "epoch": 0.75,
      "learning_rate": 5e-06,
      "loss": 0.2178,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 1000,
  "total_flos": 2.30868320256e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}